Sciweavers

1188 search results - page 204 / 238
» States of Knowledge
Sort
View
92
Voted
NDSS
2007
IEEE
15 years 4 months ago
Attribute-Based Publishing with Hidden Credentials and Hidden Policies
With Hidden Credentials Alice can send policyencrypted data to Bob in such a way that he can decrypt the data only with the right combination of credentials. Alice gains no knowle...
Apu Kapadia, Patrick P. Tsang, Sean W. Smith
ATAL
2007
Springer
15 years 4 months ago
IFSA: incremental feature-set augmentation for reinforcement learning tasks
Reinforcement learning is a popular and successful framework for many agent-related problems because only limited environmental feedback is necessary for learning. While many algo...
Mazda Ahmadi, Matthew E. Taylor, Peter Stone
92
Voted
ATAL
2007
Springer
15 years 4 months ago
Multiagent reinforcement learning and self-organization in a network of agents
To cope with large scale, agents are usually organized in a network such that an agent interacts only with its immediate neighbors in the network. Reinforcement learning technique...
Sherief Abdallah, Victor R. Lesser
89
Voted
EUROCAST
2007
Springer
182views Hardware» more  EUROCAST 2007»
15 years 4 months ago
A k-NN Based Perception Scheme for Reinforcement Learning
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
José Antonio Martin H., Javier de Lope Asia...
87
Voted
SIGECOM
2006
ACM
139views ECommerce» more  SIGECOM 2006»
15 years 4 months ago
Playing games in many possible worlds
In traditional game theory, players are typically endowed with exogenously given knowledge of the structure of the game—either full omniscient knowledge or partial but fixed in...
Matt Lepinski, David Liben-Nowell, Seth Gilbert, A...